This paper presents an Artificial Neural Network based algorithm to estimate the sideslip angle of a vehicle in different road conditions. The method is on two parallel tasks: (a) estimation three conditions, namely dry, wet and icy, by means separate regression networks, (b) identification condition with pattern recognition classifier allowing select correct output among network outputs. classification networks are trained datasets recorded during driving sessions conducted high-performance...

This paper proposes a method for the combined estimation of state charge (SOC) and health (SOH) batteries in hybrid full electric vehicles. The technique is based on set five artificial neural networks that are used to tackle regression classification task. In method, SOC relies identification ageing battery SOH depends behavior recursive closed-loop. designed by means training datasets collected during experimental characterizations conducted laboratory environment. lithium pack adopted...

This paper presents a tradeoff analysis in terms of accuracy and computational cost between different architectures artificial neural networks for the State Charge (SOC) estimation lithium batteries hybrid electric vehicles. The considered layouts are partly selected from literature on SOC estimation, novel proposals that have been demonstrated to be effective executing tasks other engineering fields. One architectures, Nonlinear Autoregressive Neural Network with Exogenous Input (NARX), is...

<div class="section abstract"><div class="htmlview paragraph">In modern automotive powertrains, the front-end accessory drive represents a crucial subsystem that guarantees proper functioning of micro and mild hybrid configurations auxiliary vehicle functionalities. The motor/generator (12 V or 48 V), air conditioning compressor other accessories rely on this subsystem. Therein, poly-V belt is main transmission mechanism. From an efficiency standpoint, its behavior usually...

This paper presents a local trajectory planning and control method based on the Rapidly-exploring Random Tree algorithm for autonomous racing vehicles. The aims to provide an allowing compute planned in unknown environment, structured with non-crossable obstacles, such as traffic cones. investigated exploits perception pipeline sense surrounding environment by means of LIDAR-based sensor high-performance Graphic Processing Unit. considered vehicle is four-wheel drive electric prototype,...

This paper presents an algorithm based on Artificial Neural Networks (ANNs) for the estimation of State Health (SOH) in Lithium batteries. The method exploits a feed-forward pattern recognition classifier trained with datasets collected at different temperatures and predefined current mean value discharging profile. During real implementation, scans time history battery load analyses it buffers 60 seconds. Whenever same conditions training dataset are encountered during scanning (i.e....

Battery electric vehicles (BEVs) face challenges like their limited all-electric range, the discrepancy between promised and actual energy efficiency, battery health degradation, despite environmental benefits. This article proposes an optimal adaptive cruise control (OACC) framework by leveraging ideal vehicle-to-vehicle communication to address these challenges. In a connected vehicle environment, where it is assumed that Ego vehicle’s unit (VCU) accurately knows speed position of Leading...

The vibration control of rotors for gas or steam turbines is usually performed using passive dampers when hydrodynamic bearings are not used. In layouts where the rotating parts supported by rolling bearings, damping provided squeeze film dampers. Their nature and variability their performances with temperature frequency represent main disadvantages. Dampers magnetorheological electrorheological fluid allow solving only a part abovementioned drawbacks. Active magnetic (AMBs) promising since...

Abstract The Hyperloop transportation system paradigm has gained increasing attention in the last years due to its potential advantages technology, territory, and infrastructure. From an engineering point of view, it would lead fast, safe, efficient passengers cargo. stability electrodynamic levitation represents a key enabling aspect Hyperloop. In this context, state art presents numerous attempts stabilize these systems without definitive guidelines on how attain proper, stable behavior....

This paper presents a method to design Model Predictive Control maximize the passengers’ comfort in assisted and self-driving vehicles by achieving lateral longitudinal dynamic. The weighting parameters of MPC are tuned off-line using Genetic Algorithm simultaneously control performance tracking speed profile, deviation relative yaw angle optimize perceived passengers. To this end, two evaluation indexes extracted ISO 2631 used evaluate amount vibration transmitted passengers probability...

This paper presents the design and hardware-in-the-loop (HIL) experimental validation of a data-driven estimation method for state charge (SOC) in lithium-ion batteries used hybrid electric vehicles (HEVs). The considered system features 1.25 kWh 48 V battery that is numerically modeled via an RC equivalent circuit model can also consider environmental temperature influence. proposed technique relies on nonlinear autoregressive with exogenous input (NARX) artificial neural networks (ANNs)...

In the context of automated driving, Electric Power Steering (EPS) systems represent an enabling technology. They introduce ergonomic function reducing physical effort required by driver during steering maneuver. Furthermore, EPS gives possibility high precision control system, thus paving way to autonomous driving capability. this context, present work presents a performance assessment system designed for full-electric all-wheel-drive electric prototype racing in Formula Student Driverless...

This paper presents the study of linear Offset-Free Model Predictive Control (OF-MPC) for an Active Magnetic Bearing (AMB) application. The method exploits advantages classical MPC in terms stability and control performance and, at same time, overcomes effects plant-model mismatch on reference tracking. proposed approach is based a disturbance observer with augmented plant model including input estimation. Besides abovementioned advantages, this architecture allows real-time estimation...

Self-driving vehicles have experienced an increase in research interest the last decades. Nevertheless, fully autonomous are still far from being a common means of transport. This paper presents design and experimental validation processor-in-the-loop (PIL) architecture for sports car. The considered vehicle is all-wheel drive full-electric single-seater prototype. retained PIL includes all modules required driving at system level: environment perception, trajectory planning, control....

This article investigates the economic viability of replacing high-voltage battery pack a power-split hybrid electric vehicle (HEV) and plug-in (PHEV) by estimating impact aging on fuel economy, drivability capability, range. The HEV is modeled first, an optimal energy management strategy based dynamic programming then implemented, experimental characterization data for cell presented. batteries are tested to heavily aged state, with up 84% loss capacity. payback period estimated assessing...

This paper presents an active magnetic levitation application that exploits the measurement of coil current and flux density to determine displacement mover. To this end, nonlinear behavior plant physical sensing principle are modeled with a finite element approach at different air gap lengths currents. A linear dynamic model is then obtained operating point as well relation for estimates. The effectiveness modeling performance control techniques validated experimentally on system. results...

From an athlete’s perspective, the identification of falls during rock climbing is major importance. It constitutes a solid performance indicator, but more importantly, it could be used to trigger instantaneous alarm rescue teams, thus reducing negative health consequences for climber. In this context, artificial neural network–based technique fall detection presented in study. The output tool safety and monitoring purposes. proposed method exploits network binary pattern recognition. This...

A P0 system is used in hybrid automobiles to improve engine economy and performance. An essential element of the for effectively transmitting power drive train belt (BDS). The features electric machine (EM) internal combustion engines (ICE) are taken into account by standard energy management systems, such as equivalent consumption minimization strategy (ECMS). In order maximize effectiveness system, this work provides a novel formulation ECMS, which considers loss map BDS addition...

Among many emerging technologies, battery electric vehicles (BEVs) have emerged as a prominent and highly supported solution to stringent emissions regulations. However, despite their increasing popularity, key challenges that might jeopardize further spread are the lack of charging infrastructure, life degradation, discrepancy between actual promised all-electric driving range. The primary focus this paper is formulate an integrated energy thermal comfort management (IETM) strategy. This...

The aim of this paper is to propose a methodology for the modelling, testing, and parameter identification viscoelastic supports rotating machines at component system level. Although use type dampers common in rotordynamic applications, strict dependence on working frequency material parameters makes their behavior hard predict recommends grounding design experimental data characteristics. A dedicated test rig adopted characterize validate modelling approach procedure carried out from...